{"type":"ScholarlyArticle","title":"Spherical Physics-Informed Neural Operator with Multi-Scale Coupling for Meteorological Downscaling","authors":[{"name":"Yiqiang Ye","slug":"yiqiang-ye","given":"Yiqiang","family":"Ye","affiliation":""},{"name":"Yichi Wang","slug":"yichi-wang","given":"Yichi","family":"Wang","affiliation":""},{"name":"Jiawei Wen","slug":"jiawei-wen","given":"Jiawei","family":"Wen","affiliation":""},{"name":"Jiahui Jiang","slug":"jiahui-jiang","given":"Jiahui","family":"Jiang","affiliation":""},{"name":"Zhaoyu Zhong","slug":"zhaoyu-zhong","given":"Zhaoyu","family":"Zhong","affiliation":""},{"name":"Jiangjian Yu","slug":"jiangjian-yu","given":"Jiangjian","family":"Yu","affiliation":""},{"name":"Chunxia Xiao","slug":"chunxia-xiao","given":"Chunxia","family":"Xiao","affiliation":""},{"name":"Haodi Zhang","slug":"haodi-zhang","given":"Haodi","family":"Zhang","affiliation":""}],"abstract":"Meteorological downscaling is crucial for high-resolution regional climate forecasting and disaster early warning. While neural operators have emerged as a promising paradigm for modeling complex spatiotemporal mappings, existing frameworks often struggle with spherical manifold geometric distortions, inherent atmospheric multi-scale coupling mismatches, and lack of explicit atmospheric laws. We propose the Spherical Physics-informed Neural Operator, which utilizes a Spherical Laplacian Decomposition to partition atmospheric fields into hierarchical frequency components, maintaining exact point-wise correspondence across scales.  To evaluate these representations at arbitrary locations, we introduce a localized spherical integral operator that approximates continuous kernel transforms via geometry-aware attention.  Dynamical consistency is further enforced by embedding differentiable constraints into the learning process.  Extensive experiments demonstrate that our framework attains superior accuracy and zero-shot generalization across various meteorological variables and unseen queries, representing a robust and interpretable solution for global-to-regional meteorological downscaling.","doi":"10.24963/ijcai.2026/734","url":"https://ijcai.org/proceedings/2026/734","pdf":"https://ijcai.org/proceedings/2026/0734.pdf","markdown":"https://ijcai.org/proceedings/2026/734.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/734","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"AI4Tech: AI Enabling Technologies","track":"AI4Tech: AI Enabling Technologies","number":734,"pages":{"first":6600,"last":6608},"keywords":["Domain-specific AI4Tech: Other AI4Tech applications"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}